20 research outputs found
The influence of frame length on speaker identification performance
No full textSpeaker recognition/identification is a challenge for the implementation of security applications. Unfortunately, degradation in performance is usually observed for high pitched speakers and also whenever average pitch varies significantly between enrolment and testing. In this paper, a study on the impact of the frame length used to extract features from speech signal on the performance of speaker identification is presented. Tests have been carried out on a text-dependent database. Results show that a combination of different frame sizes between the training and the recognition phases can cope with the degradation. A reduction between 40% and 65% in false rejections has been generally observed. © 2007 IEEE
Speaker identification by multi-frame generative models
No full textIn this paper an approach called Multi-Frame Speaker Models (MFS) is proposed, in order to cope with performance degradation generally observed over (short and medium) time and trials in Speaker Identification's task. The approach, based on generative models, uses multiple frame's length for speech processing in training and testing phase. A complete multi-expert system is also presented which is able to implement the proposed approach on the whole set of speakers and to obtain a near optimum for the ER's reduction. © 2008 IEEE
Seeing or Not Seeing Your Conversational Partner: The Influence of Interaction Modality on Prosodic Entrainment
No full textIn speech entrainment research, a less investigated yet crucial aspect for modelling multimodal interactive dialogue systems is the influence of inter-action modality, i.e. whether conversational partners who are visible to each other would entrain their speech more with respect to when eye contact is inhibited, or not. In our study, we compared prosodic adaptation behaviour (convergence and synchrony) of the same speaker pairs involved in collaborative game sessions under two conditions: audiovisual vs audio-only interaction. Results provide a complex picture, with a tendency to vocal entrainment enhancement when the speech/audio channel is the only one available
Prosodic convergence in Italian game dialogues
No full textIn this study we explore the manifestation of prosodic convergence between pairs of Italian speakers involved in a non-competitive game. Results show evidence of prosodic convergence and/or divergence between partners, where prosodic parameters and coordination strategies involved can vary across dialogue pairs. Also, degree of asymmetry in prosodic convergerce appears to be related to speaker empathy
Measuring prosodic entrainment in Italian collaborative game-based dialogues
No full textIn a large number of studies, it has been observed that conversational partners tend to adapt each other’s speech over the course of the interaction. This phenomenon, variously named as entrainment, coordination, alignment or adaptation, is widely believed to be crucial to mutual understanding and suc-cessful communication in human interaction. Modelling human adaptation in speech behaviour would also be very important for improving naturalness in voiced-based human-machine interaction systems. Recently, a body of research in this field has been devoted to find evidence of prosodic entrainment by measuring a number of acoustic-prosodic parameters in some languages, yet not in Italian. Our study offers a contribution to this research line. We analysed game-based collaborative dialogues between Italian speakers, by measuring their articulation rate, pitch range, pitch level and loudness. Results show some evidence of overall speech coordination (convergence and synchrony) between conversational partners, wherein the combination of specific prosodic parame-ters involved may vary across dialogues. Our results are in line with those ob-tained in previous studies on other languages, thus contributing to providing a useful basis for modelling prosodic adaptation in multilingual spoken dialogue systems
Assessing the impact of vegetation cover changes and post-fire effects through an enhanced sediment flow connectivity index (SfCI)
No full textLand cover plays a fundamental role in surface dynamics that involve sediment connectivity. Land cover types can physically mitigate, prevent or increase sediment production and mobility on the surface. Further, changes in land cover, particularly in vegetation classes, can directly affect these processes, especially if they occur over short time periods or even more rapidly after extreme events such as fires. This study analyses vegetation cover changes in the Lama Camaggi catchment (southern Italy) in relation to its sediment connectivity pattern, described by Sediment flow Connectivity Index (SfCI). The Normalized difference vegetation index (NDVI), derived from satellite data, is utilized to detect vegetation cover changes over 8-year interval and following fire events. The main objective is to evaluate how the NDVI improves the flexibility of SfCI in defining surface dynamics on both spatial and temporal scales. The findings indicate that (1) NDVI changes identify vegetation cover changes in a short period in many areas of the catchment, potentially affecting sediment connectivity, and (2) the implementation of NDVI in the SfCI helps detect post-fire effects on sediment mobility and connectivity. Integrating NDVI enhances the SfCI algorithm providing a more dynamic description of sediment patterns
Integrating Audio and Visual Information for Modelling Communicative Behaviours Perceived as Different
No full textIn human face-to-face interaction, participants can rely on a number of audio-visual information for interpreting interlocutors’ communicative intentions, such information strongly contributing to the successfulness of communication. Modelling these typical human abilities represents a main objective in human communication research, including technological applications like human-machine interaction. In this pilot study we explore the possibility of using audio-visual parameters for describing/measuring the differences perceived in interlocutor’s communicative behaviours. Preliminary results derived from the multimodal analysis of a single subject seem to indicate that measuring the distribution of some prosodic and hand gesture events which are temporally co-occurring contribute to the accounting of such perceived differences. Moreover, as far as gesture events are concerned, it has been observed that relevant information are not simply to be found in the occurences of single gestures, but mainly in some gesture modalities (for example, “single stroke ” vs “multiple stroke ” gestures, one-hand vs both-hands gestures, etc…). In this paper we also introduce and describe a software package, ViSuite, we developed for multimodal processing and used for the work described in this paper. 1
Application of Hydrological and Hydrogeological Models for Evaluating Groundwater Budget in a Shallow Aquifer in a Semi-Arid Region Under Three Pumping Rate Scenarios (Tavoliere di Puglia, Italy)
No full textWe analyze the variation in groundwater budget by modeling an aquifer in a semi-arid region in southern Italy, using different good pumping scenarios. This aquifer is overexploited due to the agricultural vocation of the area. We propose an integrated method to assess the distribution of hydrogeological parameters and the recharge rates. The hydrogeological parametrization is performed through a hydrostratigraphic approach using the geostatistical tool. Recharge rates are computed through a soil water balance application, using different monitoring stations over the area for the whole period of interest. Integrating the results of this analysis with pumping scenarios based on the water irrigation requirement of the main crops in the area, different water budgets are estimated. The results show how different pumping scenarios affect the availability of water resources and thus underline the importance of management. This integrated hydrogeological model can be applied to other areas with similar hydrogeological characteristics, and it can be considered a valuable tool for evaluating sustainable groundwater management strategies, considering land use practices and socio-economic factors
